Machine Learning
Introduction to Machine Learning.
If you love technology or have taken software engineering, or data science I am certain you have come across or heard about Machine learning.
We have witnessed technology grow and become better year after year. Things like voice recognition or even image recognition were not deemed possible in the early 2000s.
However, due to Machine learning these tasks which are especially very vital in the world today have been made possible.
We can certainly say that Machine Learning has resulted into a technological revolution. For instance, building the Amazon Alexa in the year 2000 would not have been possible but as machine learning has grown and developed over the years, we have seen an advancement in this field
SO, WHAT IS MACHINE LEARNING?
Machine learning is the science of getting computers to learn without being explicitly programmed.
Note: Through machine learning developers are able to write software which can learn how to solve a problem without actually providing step by step instructions to it.
There are three types of machine learning methods.
1. Supervised learning
2. Unsupervised learning
3. Reinforcement learning
Supervised learning: This is typically when we are given a data set and we already know what the correct output should look like
Supervised learning problems are categorized into Regression and Classification problems
- Regression: This is when we are trying to predict results within a continuous output. For instance, when we try to estimate the price of a new apartment based on a historical data set containing transacted prices and characteristics of apartments such as size, number of rooms or post code,this is a continuous outcome.
- Classification: This is when we are trying to predict results based on a. discrete output. For instance, when we are trying to estimate whether a customer would actually default on their loan or not.
Unsupervised learning: This refers to when we approach problems with little or no idea what our results should look like. We can derive structure from data where we don’t necessarily know the effect of the variables. We do this by clustering the data based on relationships among the variables in the data.
Unsupervised learning is typically used when you do not know how to classify or cluster your data and you need the algorithm to find patterns and classify the data for you.
Reinforcement learning: This is where the machine learns by trying to maximize a reward. This for instance is how you learned to play Super Mario by trial and error.
Reinforcement learning algorithms learn to perform a task simply by doing it and by trying to maximize a reward.
An example is IBM’s Deep Blue used reinforcement learning to learn chess and eventually defeated the world chess champion Gary Kasparov in 1997.
Conclusion.
- Machine learning has grown to be very important especially because it can be used to automate a lot of tasks.
- This article is supposed to give you a basic introduction to what machine learning is as you get immersed into the field in future articles.
- Feel free to have a look at the rest of the Machine learning articles that I have written.
